INDEX

Explanations

contractions with a negative connotation

oai_token-act-pair · gpt-3.5-turbo

instances of the word "wouldn't" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ULT

-0.77

PI

-0.74

dimensional

-0.61

æ³

-0.60

ipel

-0.59

 Proced

-0.59

 VERS

-0.59

 Butt

-0.58

otype

-0.58

agency

-0.57

POSITIVE LOGITS

't

1.22

geon

0.92

atically

0.86

geons

0.81

acies

0.77

atters

0.77

itial

0.77

agy

0.77

ģĸ

0.76

etsk

0.76

Activations Density 0.018%

contractions with a negative connotation

instances of the word "wouldn't" in various contexts

No Comments

No Known Activations